MB
Michiel A. Bakker
cs.AIcs.CYcs.LGcs.HCcs.MAcs.CLcs.SIquant-phcond-mat.mes-hallcs.DB
On Valency
published · living versionsW_62zqap7r·v1 · currentpublished
Designing Behavioral Profiles for Language Model Simulation of Out-of-Distribution Human Behavior
with Robin Na, Kehang Zhu, Logan Cross
1 version
W_d5gw9n6e·v1published
Preprints & journals
47 papers in the corpus · 2018–2026Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce2608.14825v3 · Zeyuan Li, Lukas Petersson, Alessandro Acquisti et al.2026 · 0 citationsarXiv
A Roadmap to Impactful Pluralistic Alignment Research2607.22305v1 · Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh et al.2026 · 0 citationsarXiv
Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems2607.21627v1 · Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker2026 · 0 citationsarXiv
Habermolt: Delegating Deliberation to AI Representatives2605.24413v3 · Joseph Low, Oscar Duys, Claude Formanek et al.2026 · 0 citationsarXiv
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation2605.15343v1 · Joshua C. Yang, Maurice Flechtner, Damian Dailisan et al.2026 · 0 citationsarXiv
Europe and the Geopolitics of AGI: The Need for a Preparedness Plan2605.13634v1 · Maximilian Negele, Daan Juijn, Afek Shamir et al.2026 · 0 citationsarXiv
AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent2604.05368v1 · Suyash Fulay, Prerna Ravi, Emily Kubin et al.2026 · 0 citationsarXiv
AI Assistance Reduces Persistence and Hurts Independent Performance2604.04721v6 · Grace Liu, Brian Christian, Tsvetomira Dumbalska et al.2026 · 3 citationsarXiv
AI Fact-Checking in the Wild: A Field Evaluation of LLM-Written Community Notes on X2604.02592v3 · Haiwen Li, Michiel A. Bakker2026 · 0 citationsarXiv
Multi-User Large Language Model Agents2604.08567v2 · Shu Yang, Shenzhe Zhu, Hao Zhu et al.2026 · 0 citationsarXiv
Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice2603.07339v3 · Prerna Ravi, Om Gokhale, Suyash Fulay et al.2026 · 0 citationsarXiv
Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift2603.26676v1 · Michelle Vaccaro, Jaeyoon Song, Abdullah Almaatouq et al.2026 · 0 citationsarXiv
Can AI mediation improve democratic deliberation?2601.05904v1 · Michael Henry Tessler, Georgina Evans, Michiel A. Bakker et al.2026 · 0 citationsKnight Institute for the First Amendment at Columbia University Symposium on "AI and Democratic Freedoms", April 10-11, 2025
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value2512.03399v1 · Joe Edelman, Tan Zhi-Xuan, Ryan Lowe et al.2025 · 0 citationsarXiv
Benchmarking Overton Pluralism in LLMs2512.01351v2 · Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen et al.2025 · 0 citationsarXiv
Shareholder Democracy with AI Representatives2510.23475v1 · Suyash Fulay, Sercan Demir, Galen Hines-Pierce et al.2025 · 0 citationsarXiv
From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM2510.12689v2 · Suyash Fulay, Jocelyn Zhu, Michiel Bakker2025 · 0 citationsarXiv
Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs2510.05154v5 · Shenzhe Zhu, Shu Yang, Michiel A. Bakker et al.2025 · 1 citationarXiv
The impact of advanced AI systems on democracy.41034566 · Summerfield, Christopher, Argyle, Lisa P, Bakker, Michiel et al.2025 · 16 citationsNature human behaviour. 2025;9(12):2420-2430
RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment2509.24159v4 · Xiaoyang Cao, Zelai Xu, Mo Guang et al.2025 · 0 citationsarXiv
Scaling Human Judgment in Community Notes with LLMs2506.24118v1 · Haiwen Li, Soham De, Manon Revel et al.2025 · 4 citationsarXiv
Perceptual interventions ameliorate statistical discrimination in learning agents.40523185 · Duéñez-Guzmán, Edgar A, Comanescu, Ramona, Mao, Yiran et al.2025 · 3 citationsProceedings of the National Academy of Sciences of the United States of America. 2025;122(25):e2319933121
Community Moderation and the New Epistemology of Fact Checking on Social Media2505.20067v1 · Isabelle Augenstein, Michiel Bakker, Tanmoy Chakraborty et al.2025 · 2 citationsarXiv
Value Profiles for Encoding Human Variation2503.15484v2 · Taylor Sorensen, Pushkar Mishra, Roma Patel et al.2025 · 4 citationsarXiv
Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders2503.01769v3 · Andrew Konya, Luke Thorburn, Wasim Almasri et al.2025 · 8 citationsarXiv
Tell Me Why: Incentivizing Explanations2502.13410v1 · Siddarth Srinivasan, Ezra Karger, Michiel Bakker et al.2025 · 0 citationsarXiv
Language Agents as Digital Representatives in Collective Decision-Making2502.09369v1 · Daniel Jarrett, Miruna Pislar, Michiel A. Bakker et al.2025 · 8 citationsarXiv
AI and the Future of Digital Public Squares2412.09988v1 · Beth Goldberg, Diana Acosta-Navas, Michiel Bakker et al.2024 · 5 citationsarXiv
Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work2411.09222v4 · Aviv Ovadya, Kyle Redman, Luke Thorburn et al.2024 · 3 citationsarXiv
Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking2411.06116v1 · Soham De, Michiel A. Bakker, Jay Baxter et al.2024 · 10 citationsarXiv
AI can help humans find common ground in democratic deliberation.39418380 · Tessler, Michael Henry, Bakker, Michiel A, Jarrett, Daniel et al.2024 · 198 citationsScience (New York, N.Y.). 2024;386(6719):eadq2852
How large language models can reshape collective intelligence.39304760 · Burton, Jason W, Lopez-Lopez, Ezequiel, Hechtlinger, Shahar et al.2024 · 116 citationsNature human behaviour. 2024;8(9):1643-1655
How will advanced AI systems impact democracy?2409.06729v1 · Christopher Summerfield, Lisa Argyle, Michiel Bakker et al.2024 · 5 citationsarXiv
Scaffolding cooperation in human groups with deep reinforcement learning.37679439 · McKee, Kevin R, Tacchetti, Andrea, Bakker, Michiel A et al.2023 · 37 citationsNature human behaviour. 2023;7(10):1787-1796
Fine-tuning language models to find agreement among humans with diverse preferences2211.15006v1 · Michiel A. Bakker, Martin J. Chadwick, Hannah R. Sheahan et al.2022 · 133 citationsarXiv
Quantifying the importance and location of SARS-CoV-2 transmission events in large metropolitan areas.35696558 · Aleta, Alberto, Martín-Corral, David, Bakker, Michiel A et al.2022 · 73 citationsProceedings of the National Academy of Sciences of the United States of America. 2022;119(26):e2112182119
Statistical discrimination in learning agents2110.11404v1 · Edgar A. Du'enez-Guzm'an, Kevin R. McKee, Yiran Mao et al.2021 · 1 citationarXiv
Modelling Cooperation in Network Games with Spatio-Temporal Complexity2102.06911v1 · Michiel A. Bakker, Richard Everett, Laura Weidinger et al.2021 · 3 citationsarXiv
Assessing Disease Exposure Risk with Location Data: A Proposal for Cryptographic Preservation of Privacy2003.14412v2 · Alex Berke, Michiel Bakker, Praneeth Vepakomma et al.2020 · 45 citationsarXiv
Atomic-scale imaging of a 27-nuclear-spin cluster using a quantum sensor.31853078 · Abobeih, M H, Randall, J, Bradley, C E et al.2020 · 280 citationsNature. 2019;576(7787):411-415
DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning1910.13983v1 · Michiel A. Bakker, Duy Patrick Tu, Humberto River'on Vald'es et al.2019 · 1 citationarXiv
Sherlock: A Deep Learning Approach to Semantic Data Type Detection1905.10688v1 · Madelon Hulsebos, Kevin Hu, Michiel Bakker et al.2019 · 15 citationsarXiv
VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository1905.04616v1 · Kevin Hu, Neil Gaikwad, Michiel Bakker et al.2019 · 10 citationsarXiv
A 10-qubit solid-state spin register with quantum memory up to one minute1905.02094v2 · C. E. Bradley, J. Randall, M. H. Abobeih et al.2019 · 544 citationsPhys. Rev. X 9, 031045 (2019)
Active Fairness in Algorithmic Decision Making1810.00031v2 · Alejandro Noriega-Campero, Michiel A. Bakker, Bernardo Garcia-Bulle et al.2018 · 74 citationsarXiv
VizML: A Machine Learning Approach to Visualization Recommendation1808.04819v1 · Kevin Z. Hu, Michiel A. Bakker, Stephen Li et al.2018 · 26 citationsarXiv
One-second coherence for a single electron spin coupled to a multi-qubit nuclear-spin environment.29959326 · Abobeih, M H, Cramer, J, Bakker, M A et al.2018 · 302 citationsNature communications. 2018;9(1):2552
Career total: 69 works. 47 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.